You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
5.**Record Statistics**: Track completion time, success rate, compute costs, tokens.
64
64
65
+
For sequence and architecture diagrams of the deploy/evaluate scripts and the Python harness, see [Workflow Diagrams](exgentic_a2a_runner/docs/workflow-diagrams.md).
66
+
65
67
## Benchmarks
66
68
67
69
The runner currently drives three benchmarks via the Exgentic MCP server. Each is a separate MCP image, pulled from `ghcr.io/exgentic/exgentic-mcp-<benchmark>:latest`, and is selected at deploy time with `--benchmark <name>`.
0 commit comments